@inproceedings{fillies-paschke-2025-improving,
title = "Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration",
author = "Fillies, Jan and
Paschke, Adrian",
editor = "Kazantseva, Anna and
Szpakowicz, Stan and
Degaetano-Ortlieb, Stefania and
Bizzoni, Yuri and
Pagel, Janis",
booktitle = "Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.latechclfl-1.14/",
doi = "10.18653/v1/2025.latechclfl-1.14",
pages = "148--159",
ISBN = "979-8-89176-241-1",
abstract = "Algorithmic hate speech detection faces significant challenges due to the diverse definitions and datasets used in research and practice. Social media platforms, legal frameworks, and institutions each apply distinct yet overlapping definitions, complicating classification efforts. This study addresses these challenges by demonstrating that existing datasets and taxonomies can be integrated into a unified model, enhancing prediction performance and reducing reliance on multiple specialized classifiers. The work introduces a universal taxonomy and a hate speech classifier capable of detecting a wide range of definitions within a single framework. Our approach is validated by combining two widely used but differently annotated datasets, showing improved classification performance on an independent test set. This work highlights the potential of dataset and taxonomy integration in advancing hate speech detection, increasing efficiency, and ensuring broader applicability across contexts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fillies-paschke-2025-improving">
<titleInfo>
<title>Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Fillies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Paschke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janis</namePart>
<namePart type="family">Pagel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-241-1</identifier>
</relatedItem>
<abstract>Algorithmic hate speech detection faces significant challenges due to the diverse definitions and datasets used in research and practice. Social media platforms, legal frameworks, and institutions each apply distinct yet overlapping definitions, complicating classification efforts. This study addresses these challenges by demonstrating that existing datasets and taxonomies can be integrated into a unified model, enhancing prediction performance and reducing reliance on multiple specialized classifiers. The work introduces a universal taxonomy and a hate speech classifier capable of detecting a wide range of definitions within a single framework. Our approach is validated by combining two widely used but differently annotated datasets, showing improved classification performance on an independent test set. This work highlights the potential of dataset and taxonomy integration in advancing hate speech detection, increasing efficiency, and ensuring broader applicability across contexts.</abstract>
<identifier type="citekey">fillies-paschke-2025-improving</identifier>
<identifier type="doi">10.18653/v1/2025.latechclfl-1.14</identifier>
<location>
<url>https://aclanthology.org/2025.latechclfl-1.14/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>148</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration
%A Fillies, Jan
%A Paschke, Adrian
%Y Kazantseva, Anna
%Y Szpakowicz, Stan
%Y Degaetano-Ortlieb, Stefania
%Y Bizzoni, Yuri
%Y Pagel, Janis
%S Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-241-1
%F fillies-paschke-2025-improving
%X Algorithmic hate speech detection faces significant challenges due to the diverse definitions and datasets used in research and practice. Social media platforms, legal frameworks, and institutions each apply distinct yet overlapping definitions, complicating classification efforts. This study addresses these challenges by demonstrating that existing datasets and taxonomies can be integrated into a unified model, enhancing prediction performance and reducing reliance on multiple specialized classifiers. The work introduces a universal taxonomy and a hate speech classifier capable of detecting a wide range of definitions within a single framework. Our approach is validated by combining two widely used but differently annotated datasets, showing improved classification performance on an independent test set. This work highlights the potential of dataset and taxonomy integration in advancing hate speech detection, increasing efficiency, and ensuring broader applicability across contexts.
%R 10.18653/v1/2025.latechclfl-1.14
%U https://aclanthology.org/2025.latechclfl-1.14/
%U https://doi.org/10.18653/v1/2025.latechclfl-1.14
%P 148-159
Markdown (Informal)
[Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration](https://aclanthology.org/2025.latechclfl-1.14/) (Fillies & Paschke, LaTeCHCLfL 2025)
ACL